@agent-sh/computer-use-linux 0.7.23 → 0.7.24

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agent-sh/computer-use-linux",
-  "version": "0.7.23",
+  "version": "0.7.24",
   "description": "Native Linux desktop control for AI agents (MCP server, Pi tools, and CLI): semantic AT-SPI accessibility trees, screenshots, compositor window targeting, Wayland/X11 input, and an on-screen activity indicator.",
   "license": "MIT",
   "type": "commonjs",

package/pi/extension/generated-tools.ts

@@ -7,9 +7,9 @@ export interface GeneratedMcpToolDefinition {
 	annotations: Record<string, unknown>;
 }
 
-export const GENERATED_SERVER_VERSION = "0.7.23";
-export const GENERATED_TOOL_CATALOG_HASH = "3e2d6cbbf31957fcdc8d05e66f959ad1c3b277685dfa30ed3c3b2f4df451eec6";
-export const GENERATED_SHELL_TOOL_CATALOG_HASH = "052c430ada325bd74fd764fc3f9d1139f4e6e401b6a5dbc6ef8a3de538214241";
+export const GENERATED_SERVER_VERSION = "0.7.24";
+export const GENERATED_TOOL_CATALOG_HASH = "dee39a43a4d642b61b861f4aa90cdabc9a416befbc10d463a005bcbb892eaf14";
+export const GENERATED_SHELL_TOOL_CATALOG_HASH = "b78f54e50d3a2d615af92ee2a2373599684f02a802b06f1226981f985e34f456";
 export const GENERATED_MCP_TOOLS =
 [
   {
@@ -963,7 +963,7 @@ export const GENERATED_MCP_TOOLS =
       "openWorldHint": true,
       "readOnlyHint": false
     },
-    "description": "Invoke an accessibility action exposed by an element selected by index, identifier, or semantic selector. Defaults to the primary action unless action is provided. Pass screenshot_after (true, \"screen\", or \"window\") or include_tree=true to return post-action observation in the same result.",
+    "description": "Invoke an accessibility action exposed by an element selected by index, identifier, or semantic selector. Defaults to the primary action unless action is provided. A stale semantic target can recover once with verified process/window ownership. Recovery invalidates cached indices; call get_app_state before further element_index actions. Pass screenshot_after (true, \"screen\", or \"window\") or include_tree=true to return post-action observation in the same result.",
     "inputSchema": {
       "$defs": {
         "ScreenshotOutputFormat": {

package/skills/computer-use-linux/SKILL.md

@@ -139,7 +139,7 @@ Pi native tools skip this MCP `command` config; see [Pi setup](references/pi-set
 4. If `can_build_accessibility_tree` is false, run `setup_accessibility` and restart the target app.
 5. If `can_query_windows` is false on GNOME Wayland, run `setup_window_targeting` and ask the user to log out and back in if setup says the shell extension needs a reload.
 6. Before targeted input, call `list_windows` or `focused_window` and verify the intended window by title, app id, pid, or wm class.
-7. Prefer semantic targeting from `get_app_state`: use element indices or role/name/text/states selectors.
+7. Prefer semantic targeting from `get_app_state`: use element indices or role/name/text/states selectors. Automatic recovery of a dead semantic target requires verified PID/window ownership and invalidates cached indices; call `get_app_state` again before further index-based actions.
 8. Use coordinates only when the UI surface has no useful accessibility tree.
 9. For text input, prefer `type_text` with a target selector (`window_id`, `pid`, `app_id`, `wm_class`, `title`, `tty`, `terminal_pid`, `terminal_command`, or `terminal_cwd`) rather than relying on current focus.
 10. After mutating actions (`click`, `drag`, `scroll`, `press_key`, `type_text`, `perform_action`, `set_value`, `activate_window`, `move_window`, `resize_window`), either pass `screenshot_after: true | "screen" | "window"` (with optional `format`, `quality`, `scale`, `max_width`, `max_height`, `max_bytes`) and/or `include_tree: true` on the action call itself to observe the result in the same tool call, or re-check state with `get_app_state`, `focused_window`, or an app-specific readback.